v2: retrain with 12288-vocab BPE (was 8192), 56,902,144 params, best val 1.3837

#4
by Compactbot - opened
No description provided.

v2 weights: 56,902,144 params, 12288-vocab, best val 1.3837

Compactbot changed pull request status to merged

Sign up or log in to comment